Implementation:Groq Groq python Speech Create

Knowledge Sources	Groq Python SDK Groq API Docs
Domains	Audio, Text_To_Speech
Last Updated	2026-02-15 16:00 GMT

Overview

Concrete tool for generating speech audio from text provided by the Groq Python SDK.

Description

The Speech.create() method POSTs to /openai/v1/audio/speech with the text, model, and voice parameters. It returns a BinaryAPIResponse containing raw audio bytes. The request includes an Accept: audio/wav header by default.

Usage

Access via client.audio.speech.create(). The three required parameters are input, model, and voice. The returned BinaryAPIResponse provides .content (bytes), .write_to_file(), and .stream_to_file() methods.

Code Reference

Source Location

• Repository: groq-python
• File: src/groq/resources/audio/speech.py
• Lines: L50-110 (sync), L133-193 (async)

Signature

class Speech(SyncAPIResource):
    def create(
        self,
        *,
        input: str,
        model: Union[str, Literal["playai-tts", "playai-tts-arabic"]],
        voice: str,
        response_format: Literal["flac", "mp3", "mulaw", "ogg", "wav"] | Omit = omit,
        sample_rate: Literal[8000, 16000, 22050, 24000, 32000, 44100, 48000] | Omit = omit,
        speed: float | Omit = omit,
    ) -> BinaryAPIResponse:

Import

from groq import Groq
# Access via: client.audio.speech.create(...)

I/O Contract

Inputs

Name	Type	Required	Description
input	str	Yes	Text to generate audio for
model	str or Literal["playai-tts", "playai-tts-arabic"]	Yes	TTS model ID
voice	str	Yes	Voice ID
response_format	Literal["flac", "mp3", "mulaw", "ogg", "wav"]	No	Audio output format
sample_rate	Literal[8000, ..., 48000]	No	Audio sample rate
speed	float	No	Speech speed

Outputs

Name	Type	Description
(return)	BinaryAPIResponse	Contains raw audio bytes; access via .content, .write_to_file(), or .stream_to_file()

Usage Examples

from groq import Groq
from pathlib import Path

client = Groq()

response = client.audio.speech.create(
    input="The quick brown fox jumps over the lazy dog.",
    model="playai-tts",
    voice="Arista-PlayAI",
    response_format="wav",
)

# Save to file
Path("output.wav").write_bytes(response.content)

# Or use the convenience method
response.write_to_file("output.wav")

Related Pages

Implements Principle

• Principle:Groq_Groq_python_Speech_Generation

Requires Environment

• Environment:Groq_Groq_python_Python_Groq_SDK